Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Implicit-need coverage on 100-query four-scene benchmark v2 (full)
Loading...
80.4
Overall Coverage
AURA Intent
19.976
35.663
51.35
67.037
Jun 4, 2026
Overall Coverage
Coverage (cafe)
Coverage (library)
Coverage (garden)
Coverage (night)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Overall Coverage
Coverage (cafe)
Coverage (library)
Coverage (garden)
Coverage (night)
AURA Intent
Backbone=gpt-4o-mini,...
2026.06
80.4
80
77.9
81.1
82.7
NoIntent
Backbone=gpt-4o-mini,...
2026.06
73.3
70.9
68.8
73.1
80.3
Literal
Backbone=gpt-4o-mini,...
2026.06
22.3
20
26.4
23.7
19.2
Feedback
Search any
task
Search any
task